chardet/charsetgroupprober.py

   1 ######################## BEGIN LICENSE BLOCK ########################
   2 # The Original Code is Mozilla Communicator client code.
   3 #
   4 # The Initial Developer of the Original Code is
   5 # Netscape Communications Corporation.
   6 # Portions created by the Initial Developer are Copyright (C) 1998
   7 # the Initial Developer. All Rights Reserved.
   8 #
   9 # Contributor(s):
  10 #   Mark Pilgrim - port to Python
  11 #
  12 # This library is free software; you can redistribute it and/or
  13 # modify it under the terms of the GNU Lesser General Public
  14 # License as published by the Free Software Foundation; either
  15 # version 2.1 of the License, or (at your option) any later version.
  16 #
  17 # This library is distributed in the hope that it will be useful,
  18 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  19 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  20 # Lesser General Public License for more details.
  21 #
  22 # You should have received a copy of the GNU Lesser General Public
  23 # License along with this library; if not, write to the Free Software
  24 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
  25 # 02110-1301  USA
  26 ######################### END LICENSE BLOCK #########################
  27
  28 import constants, sys
  29 from charsetprober import CharSetProber
  30
  31 class CharSetGroupProber(CharSetProber):
  32     def __init__(self):
  33         CharSetProber.__init__(self)
  34         self._mActiveNum = 0
  35         self._mProbers = []
  36         self._mBestGuessProber = None
  37
  38     def reset(self):
  39         CharSetProber.reset(self)
  40         self._mActiveNum = 0
  41         for prober in self._mProbers:
  42             if prober:
  43                 prober.reset()
  44                 prober.active = constants.True
  45                 self._mActiveNum += 1
  46         self._mBestGuessProber = None
  47
  48     def get_charset_name(self):
  49         if not self._mBestGuessProber:
  50             self.get_confidence()
  51             if not self._mBestGuessProber: return None
  52 #                self._mBestGuessProber = self._mProbers[0]
  53         return self._mBestGuessProber.get_charset_name()
  54
  55     def feed(self, aBuf):
  56         for prober in self._mProbers:
  57             if not prober: continue
  58             if not prober.active: continue
  59             st = prober.feed(aBuf)
  60             if not st: continue
  61             if st == constants.eFoundIt:
  62                 self._mBestGuessProber = prober
  63                 return self.get_state()
  64             elif st == constants.eNotMe:
  65                 prober.active = constants.False
  66                 self._mActiveNum -= 1
  67                 if self._mActiveNum <= 0:
  68                     self._mState = constants.eNotMe
  69                     return self.get_state()
  70         return self.get_state()
  71
  72     def get_confidence(self):
  73         st = self.get_state()
  74         if st == constants.eFoundIt:
  75             return 0.99
  76         elif st == constants.eNotMe:
  77             return 0.01
  78         bestConf = 0.0
  79         self._mBestGuessProber = None
  80         for prober in self._mProbers:
  81             if not prober: continue
  82             if not prober.active:
  83                 if constants._debug:
  84                     sys.stderr.write(prober.get_charset_name() + ' not active\n')
  85                 continue
  86             cf = prober.get_confidence()
  87             if constants._debug:
  88                 sys.stderr.write('%s confidence = %s\n' % (prober.get_charset_name(), cf))
  89             if bestConf < cf:
  90                 bestConf = cf
  91                 self._mBestGuessProber = prober
  92         if not self._mBestGuessProber: return 0.0
  93         return bestConf
  94 #        else:
  95 #            self._mBestGuessProber = self._mProbers[0]
  96 #            return self._mBestGuessProber.get_confidence()